{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:VVGQ4QLZS2IFBY4BEMBEA2I2VY","short_pith_number":"pith:VVGQ4QLZ","canonical_record":{"source":{"id":"2308.13958","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-08-26T20:59:21Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"c809cfbadca3f9a9dac3da0ab573d1ae31b1cc3f559a88495869071a080f0b21","abstract_canon_sha256":"9ece21bdbaa42958d5cd73d8edf751338854056dd7ea3a284bf33820a55a41d4"},"schema_version":"1.0"},"canonical_sha256":"ad4d0e4179969050e381230240691aae0b561ad9a24f569582e9f9bb8eb9b59d","source":{"kind":"arxiv","id":"2308.13958","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2308.13958","created_at":"2026-07-05T06:45:07Z"},{"alias_kind":"arxiv_version","alias_value":"2308.13958v1","created_at":"2026-07-05T06:45:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.13958","created_at":"2026-07-05T06:45:07Z"},{"alias_kind":"pith_short_12","alias_value":"VVGQ4QLZS2IF","created_at":"2026-07-05T06:45:07Z"},{"alias_kind":"pith_short_16","alias_value":"VVGQ4QLZS2IFBY4B","created_at":"2026-07-05T06:45:07Z"},{"alias_kind":"pith_short_8","alias_value":"VVGQ4QLZ","created_at":"2026-07-05T06:45:07Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:VVGQ4QLZS2IFBY4BEMBEA2I2VY","target":"record","payload":{"canonical_record":{"source":{"id":"2308.13958","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-08-26T20:59:21Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"c809cfbadca3f9a9dac3da0ab573d1ae31b1cc3f559a88495869071a080f0b21","abstract_canon_sha256":"9ece21bdbaa42958d5cd73d8edf751338854056dd7ea3a284bf33820a55a41d4"},"schema_version":"1.0"},"canonical_sha256":"ad4d0e4179969050e381230240691aae0b561ad9a24f569582e9f9bb8eb9b59d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:45:07.645127Z","signature_b64":"FkEBEmC4mhPM0sPLRjvuX3G3fvBILFvP493ajPYp3/3rpfgc9L+SNqbnF2kJWN827DZ6ZPGBUUY425G1EJodBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ad4d0e4179969050e381230240691aae0b561ad9a24f569582e9f9bb8eb9b59d","last_reissued_at":"2026-07-05T06:45:07.644730Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:45:07.644730Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2308.13958","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:45:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/aUF6MdG8fNOd9CWLrClAEZZtDO2hyGrrhTVpKBu6XOd01et1WctGtjov9buVvWCKGI/TRRNcmw/f6OW6kWEAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-13T09:01:35.454661Z"},"content_sha256":"13b2631dbfdf1566cd0a1eec8029dd57b385216f4a3ea4668c21f46149248087","schema_version":"1.0","event_id":"sha256:13b2631dbfdf1566cd0a1eec8029dd57b385216f4a3ea4668c21f46149248087"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:VVGQ4QLZS2IFBY4BEMBEA2I2VY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Improving Knowledge Distillation for BERT Models: Loss Functions, Mapping Methods, and Weight Tuning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Adeem Jassani, Apoorv Dankar, Kartikaeya Kumar","submitted_at":"2023-08-26T20:59:21Z","abstract_excerpt":"The use of large transformer-based models such as BERT, GPT, and T5 has led to significant advancements in natural language processing. However, these models are computationally expensive, necessitating model compression techniques that reduce their size and complexity while maintaining accuracy. This project investigates and applies knowledge distillation for BERT model compression, specifically focusing on the TinyBERT student model. We explore various techniques to improve knowledge distillation, including experimentation with loss functions, transformer layer mapping methods, and tuning th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.13958","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2308.13958/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:45:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IuXmIsTCvsBNm5lIUvxo64/qc+N7gVBIIbhFa5VxkDUCHUyOVKCm3IPweZyHwmltxoeovuqPT+oqqrqmojf3Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-13T09:01:35.455030Z"},"content_sha256":"04f2712166408a45f8612b32cb89ecccd5ec28d1c97e95a8015d9164a35506f1","schema_version":"1.0","event_id":"sha256:04f2712166408a45f8612b32cb89ecccd5ec28d1c97e95a8015d9164a35506f1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VVGQ4QLZS2IFBY4BEMBEA2I2VY/bundle.json","state_url":"https://pith.science/pith/VVGQ4QLZS2IFBY4BEMBEA2I2VY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VVGQ4QLZS2IFBY4BEMBEA2I2VY/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-13T09:01:35Z","links":{"resolver":"https://pith.science/pith/VVGQ4QLZS2IFBY4BEMBEA2I2VY","bundle":"https://pith.science/pith/VVGQ4QLZS2IFBY4BEMBEA2I2VY/bundle.json","state":"https://pith.science/pith/VVGQ4QLZS2IFBY4BEMBEA2I2VY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VVGQ4QLZS2IFBY4BEMBEA2I2VY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:VVGQ4QLZS2IFBY4BEMBEA2I2VY","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"9ece21bdbaa42958d5cd73d8edf751338854056dd7ea3a284bf33820a55a41d4","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-08-26T20:59:21Z","title_canon_sha256":"c809cfbadca3f9a9dac3da0ab573d1ae31b1cc3f559a88495869071a080f0b21"},"schema_version":"1.0","source":{"id":"2308.13958","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2308.13958","created_at":"2026-07-05T06:45:07Z"},{"alias_kind":"arxiv_version","alias_value":"2308.13958v1","created_at":"2026-07-05T06:45:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.13958","created_at":"2026-07-05T06:45:07Z"},{"alias_kind":"pith_short_12","alias_value":"VVGQ4QLZS2IF","created_at":"2026-07-05T06:45:07Z"},{"alias_kind":"pith_short_16","alias_value":"VVGQ4QLZS2IFBY4B","created_at":"2026-07-05T06:45:07Z"},{"alias_kind":"pith_short_8","alias_value":"VVGQ4QLZ","created_at":"2026-07-05T06:45:07Z"}],"graph_snapshots":[{"event_id":"sha256:04f2712166408a45f8612b32cb89ecccd5ec28d1c97e95a8015d9164a35506f1","target":"graph","created_at":"2026-07-05T06:45:07Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2308.13958/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The use of large transformer-based models such as BERT, GPT, and T5 has led to significant advancements in natural language processing. However, these models are computationally expensive, necessitating model compression techniques that reduce their size and complexity while maintaining accuracy. This project investigates and applies knowledge distillation for BERT model compression, specifically focusing on the TinyBERT student model. We explore various techniques to improve knowledge distillation, including experimentation with loss functions, transformer layer mapping methods, and tuning th","authors_text":"Adeem Jassani, Apoorv Dankar, Kartikaeya Kumar","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-08-26T20:59:21Z","title":"Improving Knowledge Distillation for BERT Models: Loss Functions, Mapping Methods, and Weight Tuning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.13958","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:13b2631dbfdf1566cd0a1eec8029dd57b385216f4a3ea4668c21f46149248087","target":"record","created_at":"2026-07-05T06:45:07Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"9ece21bdbaa42958d5cd73d8edf751338854056dd7ea3a284bf33820a55a41d4","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-08-26T20:59:21Z","title_canon_sha256":"c809cfbadca3f9a9dac3da0ab573d1ae31b1cc3f559a88495869071a080f0b21"},"schema_version":"1.0","source":{"id":"2308.13958","kind":"arxiv","version":1}},"canonical_sha256":"ad4d0e4179969050e381230240691aae0b561ad9a24f569582e9f9bb8eb9b59d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ad4d0e4179969050e381230240691aae0b561ad9a24f569582e9f9bb8eb9b59d","first_computed_at":"2026-07-05T06:45:07.644730Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:45:07.644730Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"FkEBEmC4mhPM0sPLRjvuX3G3fvBILFvP493ajPYp3/3rpfgc9L+SNqbnF2kJWN827DZ6ZPGBUUY425G1EJodBw==","signature_status":"signed_v1","signed_at":"2026-07-05T06:45:07.645127Z","signed_message":"canonical_sha256_bytes"},"source_id":"2308.13958","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:13b2631dbfdf1566cd0a1eec8029dd57b385216f4a3ea4668c21f46149248087","sha256:04f2712166408a45f8612b32cb89ecccd5ec28d1c97e95a8015d9164a35506f1"],"state_sha256":"bab52521602af594c77b4f181db46ea6f0ed93ae2cfb90edbc978141f39185cd"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mTKfSaccZ5pjW0ztmFePFsKXTrEaf4cGgcHYcSATZK8PyT5YWk/81PuGhle0zzlFg4qHTbQI8Do4Ybcv3NQfBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-13T09:01:35.457039Z","bundle_sha256":"989c3c344caa0cc623ab1f5353b1e1ecb64703b42442f4028719959706c62977"}}